Claudio Fanconi
@fanconic.bsky.social
Please insert pretentious things about myself here:
PhD student in Machine Learning @ University of Cambridge | Previously MSc & Bsc @ ETH Zürich
fanconic.github.io
PhD student in Machine Learning @ University of Cambridge | Previously MSc & Bsc @ ETH Zürich
fanconic.github.io
Our paper from the ICML 2025 workshop on Multi-Agent Systems explores a cascaded LLM framework for cost-effective decision-making. Small models defer to larger ones—or abstain for human input—based on uncertainty.
Paper: arxiv.org/abs/2506.11887
#LLM #MultiAgent #ICML2025
Paper: arxiv.org/abs/2506.11887
#LLM #MultiAgent #ICML2025
July 21, 2025 at 12:05 PM
Our paper from the ICML 2025 workshop on Multi-Agent Systems explores a cascaded LLM framework for cost-effective decision-making. Small models defer to larger ones—or abstain for human input—based on uncertainty.
Paper: arxiv.org/abs/2506.11887
#LLM #MultiAgent #ICML2025
Paper: arxiv.org/abs/2506.11887
#LLM #MultiAgent #ICML2025
Our paper from the ICML 2025 workshop on Models of Human Feedback (Oral presentation) proposes few-shot steerable alignment for LLMs, utilising neural processes to handle conflicting and unobserved preferences.
Paper: arxiv.org/abs/2412.13998
#LLM #AIAlignment #ICML2025
Paper: arxiv.org/abs/2412.13998
#LLM #AIAlignment #ICML2025
July 21, 2025 at 12:02 PM
Our paper from the ICML 2025 workshop on Models of Human Feedback (Oral presentation) proposes few-shot steerable alignment for LLMs, utilising neural processes to handle conflicting and unobserved preferences.
Paper: arxiv.org/abs/2412.13998
#LLM #AIAlignment #ICML2025
Paper: arxiv.org/abs/2412.13998
#LLM #AIAlignment #ICML2025
🎉First #NeurIPS paper: We used LLMs to discover new preference optimization algorithms through evolution - they propose code, train a separate LLM & use the performance feedback to improve. After some generations, it found multiple novel, high-performing objective functions! arxiv.org/pdf/2406.08414
November 25, 2024 at 2:05 PM
🎉First #NeurIPS paper: We used LLMs to discover new preference optimization algorithms through evolution - they propose code, train a separate LLM & use the performance feedback to improve. After some generations, it found multiple novel, high-performing objective functions! arxiv.org/pdf/2406.08414